Downloads · 30 days
10
3% of all-time downloads
gngpostalsrvc/BERiT_14500
BERiT_14500 is a fill-mask model from gngpostalsrvc. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
10
3% of all-time downloads
All-time downloads
306
Public
Repo size
1.2 GB
Likes
0
Public
Click a slice to open those files.
.bin389 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.3825 | 0.19 | 500 | 8.3006 |
| 8.2426 | 0.39 | 1000 | 8.2751 |
| 8.1622 | 0.58 | 1500 | 8.2504 |
| 8.1673 | 0.77 | 2000 | 8.1935 |
| 8.1597 | 0.97 | 2500 | 8.1928 |
| 8.0644 | 1.16 | 3000 | 8.1111 |
| 8.0724 | 1.36 | 3500 | 8.0820 |
| 8.0654 | 1.55 | 4000 | 8.0655 |
| 8.0649 | 1.74 | 4500 | 8.0896 |
| 8.051 | 1.94 | 5000 | 8.0838 |
| 8.0003 | 2.13 | 5500 | 8.0989 |
| 7.9795 | 2.32 | 6000 | 8.0729 |
| 7.9984 | 2.52 | 6500 | 8.0566 |
| 7.9935 | 2.71 | 7000 | 8.0757 |
| 7.9652 | 2.9 | 7500 | 8.0316 |